视觉计算中的字典学习进展：自适应表示与应用

需积分: 10 99 浏览量更新于2024-07-17 收藏 5.87MB PDF 举报

"《视觉计算中的字典学习》是一本深入探讨近年来在视觉计算领域快速发展的重要理论和技术。字典学习是基于稀疏表示方法的一种新兴技术，它与传统的基于人工定义的变换方法如傅立叶变换和小波变换不同，目标是通过自适应地从数据中学习出一个字典，从而实现对数据的最优稀疏表示。相比于传统的聚类算法如K-means，字典学习允许每个数据点关联一组小型原子（字典元素），提供了一种更为灵活的数据表示方式，能够更好地捕捉数据原始特征空间中的相关信息。早期的字典学习算法之一是K-SVD，这是一种迭代的算法，通过交替最小化来更新字典和稀疏系数。自K-SVD之后，研究人员提出了许多它的变种和新算法，旨在增强字典的判别性，使其更适用于特定任务，或者通过模型多个字典之间的关系来提高整体性能。在视觉计算领域，字典学习的应用广泛，尤其是在图像、视频和多媒体处理中，利用学习到的字典，解决了诸如图像去噪、图像复原、视频压缩等长期存在的挑战。该书作为《合成讲座：图像、视频及多媒体处理》系列的一部分，由Alan C. Bovik编辑，集合了世界顶尖专家的独特见解和高效传授知识的方式。系列讲座内容丰富，既包括基础概念，也有进阶技术，打破了传统的教科书形式，为读者提供了快速入门字典学习领域的全面指南。通过梳理近年来的研究进展，特别是2008年以后的相关文献，这本书为读者呈现了一个系统化的框架，涵盖了通用方法论、具体算法以及实际应用案例，对于想要在这个领域探索的人来说，是一本不可或缺的参考资料。"

xvi FIGURE CREDITS

Figure 4.1 From: Aharon, M., Elad, M., and Bruckstein, A. (2006). K-SVD: An

algorithm for designing overcomplete dictionaries for sparse represen-

tation. IEEE Transactions on Signal Processing, 54 (11), 4311-4322.

Figure 4.2 From: Bryt, O. and Elad, M. (2008). Compression of facial images

using the k-svd algorithm. Journal of Visual Communication and Image

permission.

Figure 4.4 From: Dong, W., Li, X., Zhang, D., and Shi, G. (2011a). Sparsity-

based image denoising via dictionary learning and structural cluster-

ing. In Computer Vision and Pattern Recognition (CVPR), 2011 IEEE

permission.

Figure 4.5 Mairal, J., Bach, F., Ponce, J., and Sapiro, G. (2009a). Online dictio-

nary learning for sparse coding. In Proceedings of the 26th Annual In-

ternational Conference on Machine Learning, pages 689-696. Used with

permission.

Figure 4.7 From: Mairal, J., Bach, F., Ponce, J., Sapiro, G., and Zisserman, A.

(2009b). Non-local sparse models for image restoration. In Computer

Vision, 2009 IEEE 12th International Conference on, pages 2272-2279.

Figure 4.8 From: Yang, S., Liu, Z., Wang, M., Sun, F., and Jiao, L. (2011b).

Multitask dictionary learning and sparse representation based single-

image super-resolution reconstruction. Neurocomputing, 74(17):3193-

Figure 4.9 From: Zhang, Q., Zhou, J., Wang, Y., Ye, J., and Li, B. (2014). Im-

age cosegmentation via multitask learning. In British Machine Vision

Conference. Used with permission.

Figure 4.10 From: Wright, J., Ganesh, A., Rao, S., Peng, Y., and Ma, Y. (2009a).

Robust principal component analysis: Exact recovery of corrupted low-

rank matrices by convex optimization. In Proc. of Neural Information

Processing Systems, volume 3. Used with permission.

Figure 4.11 From: Yan, J., Zhu, M., Liu, H., and Liu, Y. (2010). Visual saliency de-

tection via sparsity pursuit. Signal Processing Letters, IEEE, 17(8):739-

剩余152页未读，继续阅读

giscl

粉丝: 0
资源: 15

视觉计算中的字典学习进展：自适应表示与应用

Introduction to Visual Computing: Core Concepts in Computer Vision, Graphics

Convolutional Neural Networks in Visual Computing A Concise Guide 无水印原版pdf

Advances in Soft Computing and Machine Learning in Image Processing 无水印pdf

Advances in Soft Computing and Machine Learning in Image Processing (2018)

Introduction to Visual Computing (2018)

Learning and Soft Computing (PDF En)

Mobile Cloud Visual Media Computing

Explorations in Quantum Computing

Soft Computing in Machine Learning(PDF)

Advances in Intelligent Computing epub

最新资源